Synthetic Benchmarks (continued)

TSCP

TSCP is a simple chess program, which you may read more about here. We compiled the program using our own Makefile, which you can download here. Once compiled, we ran the "bench" command inside the program. Using the -m64 flags provided no change in performance.

TSCP 1.8.1

As you can see, there appears to be no advantage with HyperThreading for this application. This also appears to be the largest lead that the Intel processor takes over the AMD during the duration of our analysis.
Update:We have retested this part of the benchmark with the -O2 flag in the correct place for both machines. The score has changed to reflect this. br>

ubench

Finally, we have ubench, which stands as the definitive Unix synthetic benchmark. Feel free to learn more about the program here. We compiled the program using ./configure and make with no optimizations. The benchmark was run on a loop ten times to assure that we were getting a true average.

Ubench 0.32 - CPU

Ubench 0.32 - MEM

Ubench 0.32 - AVG

Here, we see HyperThreading working against the Xeon processor in a distinct fashion. According to the Ubench website, both of these machines with single processors outperform dual Xeon 2.4GHz machines, even though they are only running on one processor. The program runs several math-intensive floating point and integer operations over the course of three minutes.

Synthetic Benchmarks Encryption
Comments Locked

275 Comments

View All Comments

  • fifi - Monday, August 9, 2004 - link

    oh blasted, can't edit!

    that post above was addressed to manno.
  • tfranzese - Monday, August 9, 2004 - link

    Edit buttons would be great, but anyway... I meant to say objective in place of subjective, but for anyone looking for someone's opinion there is also a link in there to a subjective view on Intel's implementation of AMD64.
  • fifi - Monday, August 9, 2004 - link

    why is it that it MUST be AMD-fans versus Intel-fans? can we not complain when we see shoddy work done?

    It's shoddy work when there's no comparison between 32-bit and 64-bit on the P4.

    It's shoddy work when the benchmarks posted are simply wrong (look to his earlier review on A3500+).

    No, it's not AT being bought by Intel. It's just plain shoddy work.

    I would have preferred if Kristopher took his time to run the benchmarks properly, and checked all the numbers are correct and ran all the control tests and present a complete picture, rather than just trying to be the first out of the door with a review on the EM64T.

    it's just plain shoddy work.

    So keep on the sarcasm and hopefully it will improve your mental abilities which are clearly being impaired by the background EM waves, you SHOULD have bought those aluminium hats like I told you to...
  • tfranzese - Monday, August 9, 2004 - link

    #55, 60, aka fanboy. Anandtech was no where the first to post Nocona benches. Not even the second, and probably not even the third.

    Here's some further Nocona reading which is far more informative and subjective for those interested that I've collected here: http://www.overclockersonline.com/index.php?page=w...

    As for this review I can only say my respect for this site has been lowered a notch. Congrats Kris and Anand!
  • Viditor - Monday, August 9, 2004 - link

    About what you'd expect between these 2 chips...

    1. 512k cache vs 1 meg cache
    2. 3.6 GHs vs 2.2 GHz
    3. single CPU (Opteron and Athlon64 perform much better as you add CPUs because of Hypertransport)

    I really feel that this review should have been held until some comparable chips could have been tested as it appears quite biased in it's present form...

    Questions though...

    1. Was the setting for the memory timing on the Athlon 64 set to 1T or 2T?
    2. Since both CPUs are 64bit, why use only 1 Gig of Ram? (4 Gig would have been a better demonstration...) The reason this is interesting is that there is some confusion as to Xeon's ability in handling larger amounts of memory well.
  • manno - Monday, August 9, 2004 - link

    Oh cry me a river you poor poor souls.

    "Alot of the benchmarks are incorrect due to setup errors. It's not just the scores that we're bitching about, but the SLOPPINESS of the review.."

    Yeah it's got to be that, and not the fact that it doesn't paint AMD as the savior of the free world. Of course!! why didn't I see that the first time a lame fanboy posted?

    God I feel so stupid!

    You know what you're right I must of been crazy to think that Anand isn't in a secret Cabal with Intel to paint The A64 in the worst possible light. Thank you... no I truly mean it from the bottom of my heart thank you for showing me the error of my ways, and keeping evil Intel, and the even more devious Anantech.com out of my life. Well I'm going to head out now and buy myself one of those shiny aluminum hats to keep them from taking over my brain waves. Take care and have fun flaming me.

    -manno
  • Xspringe - Monday, August 9, 2004 - link

    It'd be nice to see more balanced benchmark set in the next similar review with less synthetic benchmark and more benchmarks relative to real world usage. These current benchmarks aren't very useful and incomplete as has been stated by a few people before me.
  • hirschma - Monday, August 9, 2004 - link

    I'd really love to know the sizes of the executables where the Xeon won by a significant amount. I'd bet that everything just fits in the cache for the Xeon, but not for the Athlon.

    If that is, in fact, the case, then Anandtech's conclusion should be: sometimes 1 meg of cache beats 512k of cache.

    Sloppy, sloppy, sloppy.

  • WizzBall - Monday, August 9, 2004 - link

    Uh you're right manno, how awful of us to not behave and thank KK for his effort... So here it is, thank you for wasting my time Kristopher!

    And btw, what's this bs about the 'service'... if WE wouldn't come here to read on a daily basis they would have no job, get it manno? Now go back and bow again to KK, thank you very much.

    *We'll send kudos when we see something done right although it's true you can't please everybody but this time a majority of the people expressing their opinion think this is crappy work. It's weird how all the fanboys gather here on AT, huh?
  • Carfax - Monday, August 9, 2004 - link

    Manno, have you read ANY of the replies? Alot of the benchmarks are incorrect due to setup errors. It's not just the scores that we're bitching about, but the SLOPPINESS of the review..

Log in

Don't have an account? Sign up now